mlsanityData to 7 Oct 2026

Simultaneous Translation Policies: From Fixed to Adaptive

arXiv 2004.13169 ↗First posted 27 Apr 2020cs.CLcited by 42

Not on the map. Why?

Abstract (arXiv)

Adaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous methods on obtaining adaptive policies either rely on complicated training process, or underperform simple fixed policies. We design an algorithm to achieve adaptive policies via a simple heuristic composition of a set of fixed policies. Experiments on Chinese -> English and German -> English show that our adaptive policies can outperform fixed ones by up to 4 BLEU points for the same latency, and more surprisingly, it even surpasses the BLEU score of full-sentence translation in the greedy mode (and very close to beam mode), but with much lower latency.

Key facts. Cited by 42 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 14; 2024: 9; 2025: 0; 2026: 1.

42 papers.

Sort:

By area:

  1. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
  2. 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 39
  3. 2021Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policycited by 32
  4. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  5. 2021Direct Simultaneous Speech-to-Text Translation Assisted by Synchronized Streaming ASRcited by 31
  6. 2023Hidden Markov Transformer for Simultaneous Machine Translationcited by 24
  7. 2024StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learningcited by 20
  8. 2022Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translationcited by 16
  9. 2022Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translationcited by 14
  10. 2022Improving Simultaneous Machine Translation with Monolingual Datacited by 13
  11. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  12. 2024Decoder-only Streaming Transformer for Simultaneous Translationcited by 11
30 more
  1. 2023Glancing Future for Simultaneous Machine Translationcited by 10
  2. 2021Direct Simultaneous Speech-to-Speech Translation with Variational Monotonic Multihead Attentioncited by 9
  3. 2022From Simultaneous to Streaming Machine Translation by Leveraging Streaming Historycited by 9
  4. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  5. 2021Simultaneous Speech Translation for Live Subtitling: from Delay to Displaycited by 8
  6. 2023Adaptive Policy with Wait-k Model for Simultaneous Translationcited by 8
  7. 2023Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023cited by 6
  8. 2023Unified Segment-to-Segment Framework for Simultaneous Sequence Generationcited by 6
  9. 2023Simul-LLM: A Framework for Exploring High-Quality Simultaneous Translation with Large Language Modelscited by 6
  10. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  11. 2022Joint Speech Translation and Named Entity Recognitioncited by 5
  12. 2024Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translationcited by 5
  13. 2021Monotonic Simultaneous Translation with Chunk-wise Reordering and Refinementcited by 4
  14. 2023LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine Translationcited by 4
  15. 2021Simultaneous Neural Machine Translation with Constituent Label Predictioncited by 3
  16. 2024Simultaneous Interpretation Corpus Construction by Large Language Models in Distant Language Paircited by 3
  17. 2021Visualization: the missing factor in Simultaneous Speech Translationcited by 2
  18. 2023The Road to Quality is Paved with Good Revisions: A Detailed Evaluation Methodology for Revision Policies in Incremental Sequence Labellingcited by 2
  19. 2023Segmentation-Free Streaming Machine Translationcited by 2
  20. 2023Enhanced Simultaneous Machine Translation with Word-level Policiescited by 2
  21. 2024Agent-SiMT: Agent-assisted Simultaneous Machine Translation with Large Language Modelscited by 2
  22. 2024Fixed and Adaptive Simultaneous Machine Translation Strategies Using Adapterscited by 2
  23. 2024PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translationcited by 2
  24. 2023CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Trainingcited by 1
  25. 2024On the Hallucination in Simultaneous Machine Translationcited by 1
  26. 2024What does it take to get state of the art in simultaneous speech-to-speech translation?cited by 1
  27. 2022Data-Driven Adaptive Simultaneous Machine Translationcited by 0
  28. 2022Mimicking Behaviors in Separated Domainscited by 0
  29. 2023Context Consistency between Training and Testing in Simultaneous Machine Translationcited by 0
  30. 2026Dual-Stream Simultaneous Translation via 2D Grid Attentioncited by 0